Skip to content

Benchmark

Arena ELO Text Factuality - Industry Software and It Services

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
162
Scores recorded
182
Sources
1
IQ weight
2.15

Score distribution

1,476.5
Mean
1,480.3
Median
36.5
Std dev
1,425.2
10th percentile
1,517.7
90th percentile
1,338.8
Min
1,338.81,546.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.15 for chat models, measured over 162 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51MiMo V2.6 Flash· LMArena data1,500.5
52GPT-5.6 LunaxHigh· LMArena data1,499.7
53GLM 5.2Max· LMArena data1,499.5
54Gemini 3.5 FlashMedium· LMArena data1,499
55Kimi K2.6· LMArena data1,498.5
56ERNIE 5.1· LMArena data1,498.1
57Gemini 3.1 Pro Preview· LMArena data1,497.6
58Claude Sonnet 4.520250929· LMArena data1,497.6
59Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,497.3
60Muse Spark· LMArena data1,496.8
61Kimi K2.5Instant· LMArena data1,495.3
62GLM 5.1· LMArena data1,493.5
63Beam 1.0 501B A23B· LMArena data1,493.3
64Claude Sonnet 5High· LMArena data1,492.6
65Inkling FP4· LMArena data1,491.9
66Step 5 Preview· LMArena data1,490.7
67GPT-6.2 SolMax· LMArena data1,489.4
68Grok 4.6High· LMArena data1,489.3
69Qwen3.7 Plus· LMArena data1,488.9
70DeepSeek V4 Pro· LMArena data1,488.3
71Gemini 3 Flash· LMArena data1,487.7
72Gemma 4 31B IT· LMArena data1,487.7
73MiMo V2 Pro· LMArena data1,487.6
74Qwen 3.8 27B· LMArena data1,487.5
75MiMo V2.5· LMArena data1,487.1
76Grok 4.20 Multi-Agent0309, beta· LMArena data1,486.9
77GPT 5.1High· LMArena data1,486.8
78Hy3 (Deep Infra)· LMArena data1,486.1
79Grok 4.20Reasoning, 0309, beta· LMArena data1,485.9
80Kimi K2.5Thinking· LMArena data1,485.9
81GPT-6.2 AstraMax· LMArena data1,485.3
82Qwen3.6 Max Preview· LMArena data1,484.8
83GLM 5· LMArena data1,484.3
84Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,484
85Qwen3 Max Preview· LMArena data1,484
86Qwen3.5 397B A17B· LMArena data1,483
87GPT-6 SolMax· LMArena data1,482.8
88DeepSeek V4 ProHigh, 20260813· LMArena data1,482.7
89GPT-5.2 Chat20260210· LMArena data1,481.1
90MiMo V2 Omni· LMArena data1,481
91GPT-5.4 miniHigh· LMArena data1,480.6
92Grok 4.20 Beta 1· LMArena data1,480.3
93Gemini 3.5 Flash Lite· LMArena data1,480.2
94Gemini 2.5 Pro· LMArena data1,479.9
95LongCat-Flash-Chat Exp2602· LMArena data1,479.6
96Claude Opus 4.120250805· LMArena data1,479.5
97ERNIE 5.00110· LMArena data1,479.4
98MiniMax M3· LMArena data1,479.2
99DeepSeek-V4-Pro PreviewHigh· LMArena data1,478.6
100Mistral Medium 3.5· LMArena data1,478.6

Showing 51–100 of 182 results.

Data credits: LMArena, CC BY 4.0 (licence)